A B C D E F G H I K L M N O P R S T U V W X Z 
All Classes All Packages

A

absMax(float[], float[]) - Static method in class deepnetts.util.Tensors
Returns array with max values for each position in the given input vectors.
absMax(Tensor, Tensor) - Static method in class deepnetts.util.Tensors
Returns tensors with max value for each component of input tensors.
absMin(float[], float[]) - Static method in class deepnetts.util.Tensors
 
absMin(Tensor, Tensor) - Static method in class deepnetts.util.Tensors
 
absPrime(float) - Static method in class deepnetts.net.layers.activation.MathFunctions
First derivative of the abs function.
AbstractLayer - Class in deepnetts.net.layers
Base class for different types of layers.
AbstractLayer() - Constructor for class deepnetts.net.layers.AbstractLayer
 
AbstractNormalizer - Class in deepnetts.data.norm
Base class to simplify implementation of custom normalization procedure.
AbstractNormalizer() - Constructor for class deepnetts.data.norm.AbstractNormalizer
 
AbstractOptimizer - Class in deepnetts.net.train.opt
Skeletal implementation of the Optimizer interface to minimize effort to implement specific optimizers.
AbstractOptimizer(AbstractLayer) - Constructor for class deepnetts.net.train.opt.AbstractOptimizer
 
accuracy - Variable in class deepnetts.eval.ClassificationMetrics.Stats
 
ActivationFunction - Interface in deepnetts.net.layers.activation
Common base interface for all activation functions used in layers.
ActivationType - Enum in deepnetts.net.layers.activation
Supported types of activation functions.
ADADELTA - deepnetts.net.train.opt.OptimizerType
 
AdaDeltaOptimizer - Class in deepnetts.net.train.opt
Implementation of ADADELTA Optimizer which is a modification od AdaGrad that uses only a limited window or previous gradients.
AdaDeltaOptimizer(AbstractLayer) - Constructor for class deepnetts.net.train.opt.AdaDeltaOptimizer
 
ADAGRAD - deepnetts.net.train.opt.OptimizerType
 
AdaGradOptimizer - Class in deepnetts.net.train.opt
Implementation of ADAGRAD Optimizer , which uses sum of squared previous gradients to adjust a global learning rate for each weight.
AdaGradOptimizer(AbstractLayer) - Constructor for class deepnetts.net.train.opt.AdaGradOptimizer
 
ADAM - deepnetts.net.train.opt.OptimizerType
 
AdamOptimizer - Class in deepnetts.net.train.opt
Implementation of Adam optimizer which is a variation of RmsProp which includes momentum-like factor.
AdamOptimizer(AbstractLayer) - Constructor for class deepnetts.net.train.opt.AdamOptimizer
 
add(float[], float[]) - Method in class deepnetts.eval.MeanSquaredError
 
add(float[], float[]) - Method in class deepnetts.eval.RootMeanSquaredError
 
add(float[], float[]) - Static method in class deepnetts.util.Tensors
Adds given vector and store result in first.
add(float, int) - Method in class deepnetts.util.Tensor
 
add(float, int, int) - Method in class deepnetts.util.Tensor
Adds specified value to matrix value at position x, y
add(float, int, int, int) - Method in class deepnetts.util.Tensor
 
add(float, int, int, int, int) - Method in class deepnetts.util.Tensor
 
add(ExampleImage) - Method in class deepnetts.data.ImageSet
Adds image to this image set.
add(Tensor) - Method in class deepnetts.util.Tensor
Adds specified tensor t to this tensor.
addConvolutionalLayer(int, int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addConvolutionalLayer(int, int, int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addConvolutionalLayer(int, int, int, int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addConvolutionalLayer(int, int, int, int, ActivationType) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addConvolutionalLayer(int, int, int, ActivationType) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addConvolutionalLayer(int, int, ActivationType) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addFullyConnectedLayer(int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addFullyConnectedLayer(int) - Method in class deepnetts.net.FeedForwardNetwork.Builder
Adds fully connected layer with specified width and Sigmoid activation function to the network.
addFullyConnectedLayer(int, ActivationType) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
Add dense layer with specified width and activation function.
addFullyConnectedLayer(int, ActivationType) - Method in class deepnetts.net.FeedForwardNetwork.Builder
Adds fully connected addLayer with specified width and activation function to the network.
addFullyConnectedLayers(int...) - Method in class deepnetts.net.FeedForwardNetwork.Builder
 
addFullyConnectedLayers(ActivationType, int...) - Method in class deepnetts.net.FeedForwardNetwork.Builder
 
addInputLayer(int) - Method in class deepnetts.net.FeedForwardNetwork.Builder
Adds input addLayer with specified width to the network.
addInputLayer(int, int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
Input layer with specified width and height, and 3 channels by default.
addInputLayer(int, int, int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
Input layer with specified width, height and number of channels (depth).
addLayer(AbstractLayer) - Method in class deepnetts.net.FeedForwardNetwork.Builder
Adds custom layer to this network (which inherits from AbstractLayer)
addListener(TrainingListener) - Method in class deepnetts.net.train.BackpropagationTrainer
 
addMaxPoolingLayer(int, int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addMaxPoolingLayer(int, int, int) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addOutputLayer(int, ActivationType) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addOutputLayer(int, ActivationType) - Method in class deepnetts.net.FeedForwardNetwork.Builder
 
addOutputLayer(int, Class<? extends OutputLayer>) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
addPatternError(float[], float[]) - Method in class deepnetts.net.loss.BinaryCrossEntropyLoss
Calculates and adds pattern error to total error, and returns output error vector for specified actual and target outputs.
addPatternError(float[], float[]) - Method in class deepnetts.net.loss.CrossEntropyLoss
Calculates and returns error vector for specified actual and target outputs.
addPatternError(float[], float[]) - Method in interface deepnetts.net.loss.LossFunction
Calculates pattern error for singe pattern for the specified predicted and target outputs, adds the error to total error, and returns the pattern error.
addPatternError(float[], float[]) - Method in class deepnetts.net.loss.MeanSquaredErrorLoss
Adds output error vector for the given predicted and target output vectors to total error sum and returns and error vector.
addRegularizationSum(float) - Method in class deepnetts.net.loss.BinaryCrossEntropyLoss
 
addRegularizationSum(float) - Method in class deepnetts.net.loss.CrossEntropyLoss
 
addRegularizationSum(float) - Method in interface deepnetts.net.loss.LossFunction
Adds specified regularization sum to total loss.
addRegularizationSum(float) - Method in class deepnetts.net.loss.MeanSquaredErrorLoss
Add regularization sum to total loss
apply(Tensor) - Method in class deepnetts.util.ImagePreprocessing
 
apply(Function<Float, Float>) - Method in class deepnetts.util.Tensor
 
apply(T) - Method in interface deepnetts.data.Preprocessing
 
applyWeightChanges() - Method in class deepnetts.net.layers.AbstractLayer
Applies weight changes to current weights Must be diferent for convolutional does nothing for MaxPooling Same for FullyConnected and OutputLayer
applyWeightChanges() - Method in class deepnetts.net.layers.ConvolutionalLayer
Apply weight changes calculated in backward pass
applyWeightChanges() - Method in class deepnetts.net.layers.FlattenLayer
 
applyWeightChanges() - Method in class deepnetts.net.layers.FullyConnectedLayer
 
applyWeightChanges() - Method in class deepnetts.net.layers.FullyConnectedLayer1
 
applyWeightChanges() - Method in class deepnetts.net.layers.InputLayer
This method does nothing in input layer
applyWeightChanges() - Method in class deepnetts.net.layers.MaxPoolingLayer
Does nothing for pooling layer since it does not have weights It just propagates deltas from next layer to previous through connections that had max activation in forward pass
applyWeightChanges() - Method in class deepnetts.net.layers.OutputLayer
Applies weight changes after one learning iteration or batch
applyWeightChanges() - Method in class deepnetts.net.NeuralNetwork
Apply calculated weight changes to all layers.
augmentImage(BufferedImage) - Static method in class deepnetts.util.ImageUtils
 
AugmentImagesTest - Class in deepnetts.util
just move 2(x) pix to left right up down
AugmentImagesTest() - Constructor for class deepnetts.util.AugmentImagesTest
 
average(ClassificationMetrics[]) - Static method in class deepnetts.eval.ClassificationMetrics
 

B

BackpropagationTrainer - Class in deepnetts.net.train
Backpropagation training algorithm for feed forward and convolutional neural networks.
BackpropagationTrainer(NeuralNetwork) - Constructor for class deepnetts.net.train.BackpropagationTrainer
Creates and instance of Backpropagation Trainer for the specified neural network.
BackpropagationTrainer(Properties) - Constructor for class deepnetts.net.train.BackpropagationTrainer
 
backward() - Method in class deepnetts.net.layers.AbstractLayer
This method should implement backward pass in subclasses
backward() - Method in class deepnetts.net.layers.ConvolutionalLayer
Backward pass for convolutional layer tweaks the weights in filters.
backward() - Method in class deepnetts.net.layers.FlattenLayer
 
backward() - Method in class deepnetts.net.layers.FullyConnectedLayer
 
backward() - Method in class deepnetts.net.layers.FullyConnectedLayer1
 
backward() - Method in class deepnetts.net.layers.InputLayer
This method does nothing in input layer
backward() - Method in interface deepnetts.net.layers.Layer
Performs weight parameters adjustment in backward pass during training of a neural network.
backward() - Method in class deepnetts.net.layers.MaxPoolingLayer
backward pass for a max(x, y) operation has a simple interpretation as only routing the gradient to the input that had the highest value in the forward pass.
backward() - Method in class deepnetts.net.layers.OutputLayer
This method implements backward pass for the output layer.
backward() - Method in class deepnetts.net.layers.SoftmaxOutputLayer
 
backward() - Method in class deepnetts.net.NeuralNetwork
 
balanceUpsample(ImageSet, Map<String, Integer>) - Static method in class deepnetts.util.ImageSetUtils
 
BINARY - deepnetts.util.ColumnType
 
BinaryCrossEntropyLoss - Class in deepnetts.net.loss
Cross Entropy Loss for binary(single output, two classes) classification.
BinaryCrossEntropyLoss(NeuralNetwork) - Constructor for class deepnetts.net.loss.BinaryCrossEntropyLoss
 
BoundingBox - Class in deepnetts.util
 
BoundingBox(int, int, int, int) - Constructor for class deepnetts.util.BoundingBox
 
BoundingBox(int, int, int, int, int) - Constructor for class deepnetts.util.BoundingBox
 
BoundingBox(int, int, int, int, int, float) - Constructor for class deepnetts.util.BoundingBox
 
BoundingBox(int, int, int, int, int, String, float) - Constructor for class deepnetts.util.BoundingBox
 
build() - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
build() - Method in class deepnetts.net.FeedForwardNetwork.Builder
 
build() - Method in class deepnetts.net.train.KFoldCrossValidation.Builder
 
builder() - Static method in class deepnetts.net.ConvolutionalNetwork
 
builder() - Static method in class deepnetts.net.FeedForwardNetwork
Returns builder for Feed Forward Network
builder() - Static method in class deepnetts.net.train.KFoldCrossValidation
 
Builder() - Constructor for class deepnetts.net.ConvolutionalNetwork.Builder
 
Builder() - Constructor for class deepnetts.net.FeedForwardNetwork.Builder
 
Builder() - Constructor for class deepnetts.net.train.KFoldCrossValidation.Builder
 

C

calculate(float) - Method in class deepnetts.net.train.opt.AbstractOptimizer
 
calculateDeltaBias(float, int) - Method in class deepnetts.net.train.opt.AdaDeltaOptimizer
 
calculateDeltaBias(float, int) - Method in class deepnetts.net.train.opt.AdaGradOptimizer
 
calculateDeltaBias(float, int) - Method in class deepnetts.net.train.opt.AdamOptimizer
 
calculateDeltaBias(float, int) - Method in class deepnetts.net.train.opt.MomentumOptimizer
 
calculateDeltaBias(float, int) - Method in interface deepnetts.net.train.opt.Optimizer
 
calculateDeltaBias(float, int) - Method in class deepnetts.net.train.opt.RmsPropOptimizer
 
calculateDeltaBias(float, int) - Method in class deepnetts.net.train.opt.SgdOptimizer
 
calculateDeltaWeight(float, int...) - Method in class deepnetts.net.train.opt.AdaDeltaOptimizer
 
calculateDeltaWeight(float, int...) - Method in class deepnetts.net.train.opt.AdaGradOptimizer
 
calculateDeltaWeight(float, int...) - Method in class deepnetts.net.train.opt.AdamOptimizer
 
calculateDeltaWeight(float, int...) - Method in class deepnetts.net.train.opt.MomentumOptimizer
 
calculateDeltaWeight(float, int...) - Method in interface deepnetts.net.train.opt.Optimizer
 
calculateDeltaWeight(float, int...) - Method in class deepnetts.net.train.opt.RmsPropOptimizer
 
calculateDeltaWeight(float, int...) - Method in class deepnetts.net.train.opt.SgdOptimizer
 
call() - Method in class deepnetts.util.CallableIntConsumer
 
CallableIntConsumer - Class in deepnetts.util
Callable int consumer.
CallableIntConsumer(int, int, IntConsumer, CyclicBarrier) - Constructor for class deepnetts.util.CallableIntConsumer
 
CENTER - deepnetts.util.ImageResize
 
CenterOnWhiteBackground - Class in deepnetts.util
Center images on backgounds and save at target path.
CenterOnWhiteBackground() - Constructor for class deepnetts.util.CenterOnWhiteBackground
 
checkLicense() - Static method in class deepnetts.core.DeepNetts
 
checkLicense() - Method in class deepnetts.util.LicenseChecker
 
ClassificationMetrics - Class in deepnetts.eval
Classification metrics for specific class.
ClassificationMetrics(int, int, int, int) - Constructor for class deepnetts.eval.ClassificationMetrics
Constructs a new classification metrics using specified arguments.
ClassificationMetrics(ConfusionMatrix) - Constructor for class deepnetts.eval.ClassificationMetrics
Constructs a new classification metrics from specified confusion matrix.
ClassificationMetrics.Stats - Class in deepnetts.eval
 
ClassifierEvaluationResult - Class in deepnetts.eval
Contains result of the classifier evaluation, which include various metrics to evaluate how good classifier is at prediction.
ClassifierEvaluationResult() - Constructor for class deepnetts.eval.ClassifierEvaluationResult
 
ClassifierEvaluator - Class in deepnetts.eval
Evaluation method for binary and multi-class classifiers.
ClassifierEvaluator() - Constructor for class deepnetts.eval.ClassifierEvaluator
 
classify(BufferedImage) - Method in class deepnetts.util.ConvolutionalImageClassifier
 
clone() - Method in class deepnetts.util.Tensor
 
COL_IDX - Static variable in interface deepnetts.net.train.opt.Optimizer
 
COL_IDX - Static variable in class deepnetts.util.Shape
 
ColorUtils - Class in deepnetts.util
 
ColumnType - Enum in deepnetts.util
 
COMPANY - Static variable in class deepnetts.util.LicenseChecker
 
ConfusionMatrix - Class in deepnetts.eval
Confusion matrix which contains classifier evaluation results (including class labels and matrix values).
ConfusionMatrix(String[]) - Constructor for class deepnetts.eval.ConfusionMatrix
Creates a new confusion matrix for specified class labels
conv(int) - Static method in class deepnetts.net.layers.Filters
 
CONVOLUTIONAL - deepnetts.net.layers.LayerType
 
CONVOLUTIONAL - deepnetts.net.NetworkType
 
ConvolutionalImageClassifier - Class in deepnetts.util
Example how to create image classifier using ConvolutionalNetwork
ConvolutionalImageClassifier(ConvolutionalNetwork) - Constructor for class deepnetts.util.ConvolutionalImageClassifier
 
ConvolutionalImageClassifier(File) - Constructor for class deepnetts.util.ConvolutionalImageClassifier
 
ConvolutionalLayer - Class in deepnetts.net.layers
Convolutional layer performs image convolution operation on outputs of a previous layer using filters.
ConvolutionalLayer(int, int, int) - Constructor for class deepnetts.net.layers.ConvolutionalLayer
Create a new instance of convolutional layer with specified filter.
ConvolutionalLayer(int, int, int, int, ActivationType) - Constructor for class deepnetts.net.layers.ConvolutionalLayer
 
ConvolutionalLayer(int, int, int, ActivationType) - Constructor for class deepnetts.net.layers.ConvolutionalLayer
 
ConvolutionalNetwork - Class in deepnetts.net
Convolutional neural network is an extension of feed forward network, which can include 2D and 3D adaptive preprocessing layers (Convolutional and MaxPooling layer), which specialized to learn to recognize features in images.
ConvolutionalNetwork.Builder - Class in deepnetts.net
Builder for convolutional neural network
copy() - Method in class deepnetts.util.Tensor
 
copy(float[], float[]) - Static method in class deepnetts.util.Tensors
 
copy(Tensor, Tensor) - Static method in class deepnetts.util.Tensors
 
copyFrom(float[]) - Method in class deepnetts.util.Tensor
 
copyOf(float[]) - Static method in class deepnetts.util.Tensors
 
correlation(float[], float[]) - Static method in class deepnetts.util.StatUtils
Pearson correlation coefficient
correlationCoefficient - Variable in class deepnetts.eval.ClassificationMetrics.Stats
 
countByClasses() - Method in class deepnetts.data.ImageSet
 
create(int, int, float[]) - Static method in class deepnetts.util.Tensor
Factory method for creating tensor instance,
create(int, int, int, float[]) - Static method in class deepnetts.util.Tensor
 
create(int, int, int, int, float[]) - Static method in class deepnetts.util.Tensor
 
create(ActivationType) - Static method in interface deepnetts.net.layers.activation.ActivationFunction
Creates and returns specified type of activation function.
create(OptimizerType, AbstractLayer) - Static method in interface deepnetts.net.train.opt.Optimizer
Factory method to create different types of optimizers
createConvolutionalNetworkFromJson(JSONObject) - Static method in class deepnetts.util.FileIO
 
createDataSetFromRawImages(String, String, int, int, boolean) - Static method in class deepnetts.util.ImageSetUtils
Creates image data set from raw images by resizing and randomly croping to target dimensions.
createFeedForwardNetworkFromJson(JSONObject) - Static method in class deepnetts.util.FileIO
 
createFrom(ConfusionMatrix) - Static method in class deepnetts.eval.ClassificationMetrics
Creates classification metrics from the given confusion matrix.
createFromFile(File) - Static method in class deepnetts.util.FileIO
 
createFromFile(File, Class<T>) - Static method in class deepnetts.util.FileIO
 
createFromFile(String, Class<T>) - Static method in class deepnetts.util.FileIO
 
createFromJson(File) - Static method in class deepnetts.util.FileIO
 
createFromJson(String) - Static method in class deepnetts.util.FileIO
 
createFromJson(JSONObject) - Static method in class deepnetts.util.FileIO
 
createImageIndex(String) - Static method in class deepnetts.util.ImageSetUtils
List all files in all subdirectories and write them into single index.txt file.index.txt is created in specifed path.
CreateImageIndex - Class in deepnetts.util
 
CreateImageIndex() - Constructor for class deepnetts.util.CreateImageIndex
 
createIndexFile(HashMap<File, BufferedImage>, String, boolean) - Static method in class deepnetts.util.ImageUtils
 
createLabelsIndex(String) - Static method in class deepnetts.util.ImageSetUtils
Creates a labels index file from subdirectories at the given path.
CreateLabelsIndex - Class in deepnetts.util
 
CreateLabelsIndex() - Constructor for class deepnetts.util.CreateLabelsIndex
 
createRandomlyCroppedImages(String, String, int, int, int) - Static method in class deepnetts.util.ImageSetUtils
 
createsTrainingSnaphots() - Method in class deepnetts.net.train.BackpropagationTrainer
 
createSubSampledImageIndex(String, String, int, boolean) - Static method in class deepnetts.util.ImageSetUtils
Copies specified number of samples of each class from
CROP - deepnetts.util.ImageResize
 
CROSS_ENTROPY - deepnetts.net.loss.LossType
Cross Entropy Loss, used for classificaton tasks, implemented by CrossEntropyLoss
CrossEntropyLoss - Class in deepnetts.net.loss
Average Cross Entropy Loss function commonly used for multi class classification problems.
CrossEntropyLoss(NeuralNetwork) - Constructor for class deepnetts.net.loss.CrossEntropyLoss
 
CsvFormat - Class in deepnetts.util
 
CsvFormat() - Constructor for class deepnetts.util.CsvFormat
 

D

DataSets - Class in deepnetts.data
Data set utility methods ans constants.
DataSets() - Constructor for class deepnetts.data.DataSets
 
DECIMAL - deepnetts.util.ColumnType
 
DecimalScaleNormalizer - Class in deepnetts.data.norm
Decimal scale normalization for the given data set.
DecimalScaleNormalizer(DataSet<MLDataItem>) - Constructor for class deepnetts.data.norm.DecimalScaleNormalizer
Creates a new instance of max normalizer initialized to max values in given data set.
DeepNetts - Class in deepnetts.core
Global configuration and settings for Deep Netts Engine.
deepnetts.core - package deepnetts.core
Core engine configuration and settings.
deepnetts.data - package deepnetts.data
Data structures and collections to provide example data to build machine learning models, and utility methods for common data manipulation.
deepnetts.data.norm - package deepnetts.data.norm
Data normalization methods, used to scale data, in order to make them suitable for use by neural network.
deepnetts.eval - package deepnetts.eval
Evaluation procedures for machine learning models, used to estimate how good models are performing for a given data.
deepnetts.net - package deepnetts.net
Neural network architectures with their corresponding builders.
deepnetts.net.layers - package deepnetts.net.layers
Neural network layers, which are main building blocks of a neural network.
deepnetts.net.layers.activation - package deepnetts.net.layers.activation
Activation functions for neural network layers.
deepnetts.net.loss - package deepnetts.net.loss
Commonly used loss functions, which are used to calculate error during the training as a difference between predicted and target output.
deepnetts.net.train - package deepnetts.net.train
Training algorithms and related utilities.
deepnetts.net.train.opt - package deepnetts.net.train.opt
Optimization methods used by training algorithm.
deepnetts.net.weights - package deepnetts.net.weights
Weights randomization techniques, used for initializing layer's internal parameters.
deepnetts.util - package deepnetts.util
Various utility classes including Tensor, image operations, multithreading, exceptions etc.
DeepNettsException - Exception in deepnetts.util
 
DeepNettsException() - Constructor for exception deepnetts.util.DeepNettsException
Creates a new instance of JDeepNettsException without detail message.
DeepNettsException(String) - Constructor for exception deepnetts.util.DeepNettsException
Constructs an instance of JDeepNettsException with the specified detail message.
DeepNettsException(String, Throwable) - Constructor for exception deepnetts.util.DeepNettsException
 
DeepNettsException(Throwable) - Constructor for exception deepnetts.util.DeepNettsException
 
DeepNettsRunner - Class in deepnetts.util
 
DeepNettsRunner() - Constructor for class deepnetts.util.DeepNettsRunner
 
DeepNettsThreadPool - Class in deepnetts.util
 
DeleteAugmentImages - Class in deepnetts.util
just move 2(x) pix to left right up down
DeleteAugmentImages() - Constructor for class deepnetts.util.DeleteAugmentImages
 
DELIMITER_COMMA - Static variable in class deepnetts.data.DataSets
 
DELIMITER_SEMICOLON - Static variable in class deepnetts.data.DataSets
 
DELIMITER_SPACE - Static variable in class deepnetts.data.DataSets
 
DELIMITER_TAB - Static variable in class deepnetts.data.DataSets
 
deNormalizeInputs(Tensor) - Method in class deepnetts.data.norm.MaxNormalizer
 
deNormalizeOutputs(Tensor) - Method in class deepnetts.data.norm.MaxNormalizer
De-normalize given output vector in-place.
DEPTH_IDX - Static variable in interface deepnetts.net.train.opt.Optimizer
 
DEPTH_IDX - Static variable in class deepnetts.util.Shape
 
DescriptiveStatistics - Class in deepnetts.util
 
DescriptiveStatistics() - Constructor for class deepnetts.util.DescriptiveStatistics
 
detectCsvFormat(String) - Static method in class deepnetts.data.DataSets
 
DEVICE_ID - Static variable in class deepnetts.util.LicenseChecker
 
div(float) - Method in class deepnetts.util.Tensor
Divide all values in this tensor with specified value.
div(float[]) - Method in class deepnetts.util.Tensor
 
div(float[], float) - Static method in class deepnetts.util.Tensors
 
div(float[], float[]) - Static method in class deepnetts.util.Tensors
 
div(Tensor) - Method in class deepnetts.util.Tensor
 

E

EMAIL - Static variable in class deepnetts.util.LicenseChecker
 
EPOCH_FINISHED - deepnetts.net.train.TrainingEvent.Type
Specifies a training epoch finished event
EPOCH_FINISHED - Static variable in class deepnetts.net.train.TrainingEvent
Specifies that training epoch has finished.
EPOCH_STARTED - deepnetts.net.train.TrainingEvent.Type
Specifies a training epoch started event
EPOCH_STARTED - Static variable in class deepnetts.net.train.TrainingEvent
Specifies that training epoch has started.
EPS - Static variable in interface deepnetts.net.train.opt.Optimizer
Smoothing term to prevent division by zero if sqr grad sum becomes zero 1e-8 should be also tried https://d2l.ai/chapter_optimization/adagrad.html 1e-6 The value to use is 1e-6, 1e-8, Keras uses 1e-7 for adam
equals(Tensor, float) - Method in class deepnetts.util.Tensor
 
equals(Object) - Method in class deepnetts.util.Tensor
 
equalsName(String) - Method in enum deepnetts.net.layers.LayerType
 
equalsName(String) - Method in enum deepnetts.net.loss.LossType
 
equalsName(String) - Method in enum deepnetts.net.NetworkType
 
evaluate(NeuralNetwork, DataSet<? extends MLDataItem>) - Method in class deepnetts.eval.ClassifierEvaluator
Performs classifier evaluation and returns classification performance metrics.
evaluate(NeuralNetwork, DataSet<? extends MLDataItem>) - Method in class deepnetts.eval.RegresionEvaluator
 
evaluateClassifier(NeuralNetwork<?>, DataSet<? extends MLDataItem>) - Static method in class deepnetts.eval.Evaluators
 
evaluateRegressor(NeuralNetwork<?>, DataSet<? extends MLDataItem>) - Static method in class deepnetts.eval.Evaluators
Evaluates specified neural network with test set, as a regression model and returns basic regression evauation metrics.
evaluator(Evaluator<NeuralNetwork, DataSet<? extends MLDataItem>>) - Method in class deepnetts.net.train.KFoldCrossValidation.Builder
 
Evaluators - Class in deepnetts.eval
Utility methods for evaluating machine learning models.
ExampleImage - Class in deepnetts.data
This class represents example image to train the network.
ExampleImage(BufferedImage) - Constructor for class deepnetts.data.ExampleImage
 
ExampleImage(BufferedImage, String) - Constructor for class deepnetts.data.ExampleImage
 
ExampleImage(BufferedImage, String, int, int) - Constructor for class deepnetts.data.ExampleImage
 
ExampleImage(File, String) - Constructor for class deepnetts.data.ExampleImage
Creates an instance of new example image with specified image and label Loads image from specified file and creates matrix structures with color information

F

FALSE_NEGATIVE - Static variable in class deepnetts.eval.ConfusionMatrix
A label for items falsely classified as negative, which are actually positive.
FALSE_POSITIVE - Static variable in class deepnetts.eval.ConfusionMatrix
A label for items falsely classified as positive, which are actually negative.
FEEDFORWARD - deepnetts.net.NetworkType
 
FeedForwardNetwork - Class in deepnetts.net
Feed forward neural network architecture, also known as Multi Layer Perceptron.
FeedForwardNetwork.Builder - Class in deepnetts.net
Builder for FeedForwardNetwork
FILE_TRAINING_PROP - Static variable in class deepnetts.util.DeepNettsRunner
 
FileIO - Class in deepnetts.util
File utilities for saving and loading neural networks.
fill(float) - Method in class deepnetts.util.Tensor
Fills the entire tensor with specified value.
fill(float[], float) - Static method in class deepnetts.util.Tensor
 
fillFourthDim(Tensor, int, float) - Static method in class deepnetts.util.Tensors
 
Filter - Class in deepnetts.net.layers
 
Filter(int) - Constructor for class deepnetts.net.layers.Filter
 
Filter(int, int) - Constructor for class deepnetts.net.layers.Filter
 
Filters - Class in deepnetts.net.layers
 
Filters() - Constructor for class deepnetts.net.layers.Filters
 
FlattenLayer - Class in deepnetts.net.layers
Just transform outputs from prev 3d layer into flat 1d tensor in formward pass backward pass will be same as backward for fc, and for 3d layers backwardFromFc Automaticly add after 2d or 3d layer to transition to fc layers.
FlattenLayer() - Constructor for class deepnetts.net.layers.FlattenLayer
 
forward() - Method in class deepnetts.net.layers.AbstractLayer
This method should implement forward pass in subclasses
forward() - Method in class deepnetts.net.layers.ConvolutionalLayer
Forward pass for convolutional layer.
forward() - Method in class deepnetts.net.layers.FlattenLayer
 
forward() - Method in class deepnetts.net.layers.FullyConnectedLayer
 
forward() - Method in class deepnetts.net.layers.FullyConnectedLayer1
 
forward() - Method in class deepnetts.net.layers.InputLayer
This method does nothing in input layer
forward() - Method in interface deepnetts.net.layers.Layer
Performs layer calculation in forward pass of a neural network.
forward() - Method in class deepnetts.net.layers.MaxPoolingLayer
Max pooling forward pass outputs the max value for each filter position.
forward() - Method in class deepnetts.net.layers.OutputLayer
This method implements forward pass for the output layer.
forward() - Method in class deepnetts.net.layers.SoftmaxOutputLayer
This method implements forward pass for the output layer.
forward() - Method in class deepnetts.net.NeuralNetwork
 
FOURTH_DIM_IDX - Static variable in interface deepnetts.net.train.opt.Optimizer
 
fScore - Variable in class deepnetts.eval.ClassificationMetrics.Stats
 
FULLY_CONNECTED - deepnetts.net.layers.LayerType
 
FullyConnectedLayer - Class in deepnetts.net.layers
Fully connected layer is used as hidden layer in the neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer.
FullyConnectedLayer(int) - Constructor for class deepnetts.net.layers.FullyConnectedLayer
Creates an instance of fully connected layer with specified width (number of neurons) and ReLU activation function.
FullyConnectedLayer(int, ActivationType) - Constructor for class deepnetts.net.layers.FullyConnectedLayer
Creates an instance of fully connected layer with specified width (number of neurons) and activation function type.
FullyConnectedLayer1 - Class in deepnetts.net.layers
Fully connected layer is used as hidden layer in the neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer.
FullyConnectedLayer1(int) - Constructor for class deepnetts.net.layers.FullyConnectedLayer1
Creates an instance of fully connected layer with specified width (number of neurons) and ReLU activation function.
FullyConnectedLayer1(int, ActivationType) - Constructor for class deepnetts.net.layers.FullyConnectedLayer1
Creates an instance of fully connected layer with specified width (number of neurons) and activation function type.

G

gaussian(float[], float, float) - Static method in class deepnetts.net.weights.RandomWeights
 
GAUSSIAN - deepnetts.net.weights.RandomWeightsType
 
generateNoisyImage(int, int, int, String) - Static method in class deepnetts.util.ImageUtils
 
generateRandomColoredImages(int, int, int, String) - Static method in class deepnetts.util.ImageUtils
Generates a specified number of randomly full colored images of a specified size.
generateRandomFilledRectImages(int, int, int, String) - Static method in class deepnetts.util.ImageUtils
 
GenerateRandomNegative - Class in deepnetts.util
 
GenerateRandomNegative() - Constructor for class deepnetts.util.GenerateRandomNegative
 
get(int) - Method in class deepnetts.util.Tensor
Gets value at specified index position.
get(int, int) - Method in class deepnetts.eval.ConfusionMatrix
Returns a value of confusion matrix at specified position.
get(int, int) - Method in class deepnetts.util.Tensor
Returns matrix value at row, col
get(int, int, int) - Method in class deepnetts.util.Tensor
Returns value at specified index [row, col, z].
get(int, int, int, int) - Method in class deepnetts.util.Tensor
 
get(String) - Method in class deepnetts.util.Parameters
 
getAccuracy() - Method in class deepnetts.eval.ClassificationMetrics
A percent of correct classiifcations/predictions for both positive and negative classes.
getActivation() - Method in class deepnetts.net.layers.AbstractLayer
 
getActivationType() - Method in class deepnetts.net.layers.AbstractLayer
 
getAllOutputs() - Method in class deepnetts.net.ConvolutionalNetwork
 
getBalancedClassificationRate() - Method in class deepnetts.eval.ClassificationMetrics
 
getBatchSize() - Method in class deepnetts.net.layers.AbstractLayer
 
getBatchSize() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getBestNetwork() - Method in class deepnetts.net.train.KFoldCrossValidation
 
getBestResult() - Method in class deepnetts.net.train.KFoldCrossValidation
 
getBiases() - Method in class deepnetts.net.layers.AbstractLayer
 
getBlue(int) - Static method in class deepnetts.util.ColorUtils
 
getBoolean(String) - Method in class deepnetts.util.Parameters
 
getCheckpointEpochs() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getClassCount() - Method in class deepnetts.eval.ConfusionMatrix
 
getClassLabel() - Method in class deepnetts.eval.ClassificationMetrics
Returns class label for
getClassLabels() - Method in class deepnetts.eval.ConfusionMatrix
 
getColorFor(float, float, float) - Static method in class deepnetts.util.ColorUtils
 
getCols() - Method in class deepnetts.util.Tensor
 
getColumnNames() - Method in class deepnetts.data.TabularDataSet
 
getColumnNames() - Method in class deepnetts.util.CsvFormat
 
getColumnTypes() - Method in class deepnetts.util.CsvFormat
 
getConfusionMatrix() - Method in class deepnetts.eval.ClassifierEvaluationResult
 
getConfusionMatrix() - Method in class deepnetts.eval.ClassifierEvaluator
 
getCurrentEpoch() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getDefault() - Static method in class deepnetts.util.RandomGenerator
 
getDelimiter() - Method in class deepnetts.data.ImageSet
 
getDelimiter() - Method in class deepnetts.util.CsvFormat
 
getDeltaBiases() - Method in class deepnetts.net.layers.AbstractLayer
 
getDeltas() - Method in class deepnetts.net.layers.AbstractLayer
 
getDeltas() - Method in interface deepnetts.net.layers.Layer
Returns layer deltas (as a tensor).
getDeltaWeights() - Method in class deepnetts.net.ConvolutionalNetwork
 
getDeltaWeights() - Method in class deepnetts.net.layers.AbstractLayer
 
getDepth() - Method in class deepnetts.net.layers.AbstractLayer
 
getDepth() - Method in class deepnetts.util.Tensor
 
getDimension(int) - Method in class deepnetts.util.Shape
 
getDimensions() - Method in class deepnetts.util.Shape
 
getDropout() - Method in class deepnetts.net.layers.FullyConnectedLayer
 
getDropout() - Method in class deepnetts.net.layers.FullyConnectedLayer1
 
getDropout() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getEarlyStopping() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getEarlyStoppingMinDelta() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getEarlyStoppingPatience() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getErrorRate() - Method in class deepnetts.eval.ClassificationMetrics
A percent of wrong classifications/predictions made.
getEvaluationMetrics() - Method in class deepnetts.eval.ClassifierEvaluator
 
getF1Score() - Method in class deepnetts.eval.ClassificationMetrics
Calculates and returns F1 score - harmonic average of recall and precision.
getFalseDiscoveryRate() - Method in class deepnetts.eval.ClassificationMetrics
When its actauly no, how often it is classified as yes
getFalseNegative() - Method in class deepnetts.eval.ConfusionMatrix
How many positive items has been (falsely) classified as negative.
getFalseNegative(int) - Method in class deepnetts.eval.ConfusionMatrix
 
getFalseNegativeRate() - Method in class deepnetts.eval.ClassificationMetrics
When its actually yes, how often does it predicts no
getFalsePositive() - Method in class deepnetts.eval.ConfusionMatrix
Returns number of false positive classifications.
getFalsePositive(int) - Method in class deepnetts.eval.ConfusionMatrix
 
getFalsePositiveRate() - Method in class deepnetts.eval.ClassificationMetrics
When it's actually no, how often does it predict yes? FP/actual no
getFile() - Method in class deepnetts.data.ExampleImage
 
getFilterDeltaWeights() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getFilterDepth() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getFilterHeight() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getFilterHeight() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
getFilters() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getFilterWidth() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getFilterWidth() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
getFloat(String) - Method in class deepnetts.util.Parameters
 
getFloat(String) - Method in class deepnetts.util.TypedProperties
 
getFourthDim() - Method in class deepnetts.util.Tensor
 
getFScore(int) - Method in class deepnetts.eval.ClassificationMetrics
Returns the F-score.
getGradients() - Method in class deepnetts.net.layers.AbstractLayer
 
getGreen(int) - Static method in class deepnetts.util.ColorUtils
 
getHeight() - Method in class deepnetts.data.ExampleImage
 
getHeight() - Method in class deepnetts.net.layers.AbstractLayer
 
getHeight() - Method in class deepnetts.net.layers.Filter
 
getHeight() - Method in class deepnetts.util.BoundingBox
 
getId() - Method in class deepnetts.util.BoundingBox
 
getImage() - Method in class deepnetts.data.ExampleImage
 
getImageType(File) - Static method in class deepnetts.util.ImageUtils
 
getInput() - Method in class deepnetts.data.ExampleImage
 
getInput() - Method in interface deepnetts.data.MLDataItem
Returns an input for machine learning model of this item.
getInput() - Method in class deepnetts.data.TabularDataSet.Item
 
getInputLayer() - Method in class deepnetts.net.NeuralNetwork
 
getInstance() - Static method in class deepnetts.core.DeepNetts
 
getInstance() - Static method in class deepnetts.util.DeepNettsThreadPool
 
getInt(String) - Method in class deepnetts.util.TypedProperties
 
getInteger(String) - Method in class deepnetts.util.Parameters
 
getInvertImages() - Method in class deepnetts.data.ImageSet
 
getL1RegSum() - Method in class deepnetts.net.NeuralNetwork
 
getL1Regularization() - Method in class deepnetts.net.layers.AbstractLayer
 
getL1WeightSum() - Method in class deepnetts.net.layers.AbstractLayer
 
getL1WeightSum() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getL1WeightSum() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
getL2RegSum() - Method in class deepnetts.net.NeuralNetwork
 
getL2Regularization() - Method in class deepnetts.net.layers.AbstractLayer
 
getL2WeightSum() - Method in class deepnetts.net.layers.AbstractLayer
 
getL2WeightSum() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getL2WeightSum() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
getLabel() - Method in class deepnetts.data.ExampleImage
 
getLabel() - Method in class deepnetts.net.NeuralNetwork
 
getLabel() - Method in class deepnetts.util.BoundingBox
 
getLabelsCount() - Method in class deepnetts.data.ImageSet
 
getLayers() - Method in class deepnetts.net.NeuralNetwork
 
getLearningRate() - Method in class deepnetts.net.layers.AbstractLayer
 
getLearningRate() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getLicenseProperties() - Method in class deepnetts.util.LicenseChecker
 
getLossFunction() - Method in class deepnetts.net.NeuralNetwork
 
getLossType() - Method in class deepnetts.net.layers.OutputLayer
 
getMacroAverage() - Method in class deepnetts.eval.ClassifierEvaluator
 
getMacroAverage() - Method in class deepnetts.net.train.KFoldCrossValidation
 
getMatthewsCorrelationCoefficient() - Method in class deepnetts.eval.ClassificationMetrics
 
getMaxEpochs() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getMaxError() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getMaxInputs() - Method in class deepnetts.data.norm.MaxNormalizer
 
getMaxOutputs() - Method in class deepnetts.data.norm.MaxNormalizer
 
getMean() - Method in class deepnetts.data.ImageSet
 
getMean() - Method in class deepnetts.util.ImagePreprocessing
 
getMeanSquaredSum() - Method in class deepnetts.eval.MeanSquaredError
Returns mean squared error
getMomentum() - Method in class deepnetts.net.layers.AbstractLayer
 
getMomentum() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getName() - Method in class deepnetts.util.Parameter
 
getNextLayer() - Method in class deepnetts.net.layers.AbstractLayer
 
getNormalizer() - Method in class deepnetts.net.NeuralNetwork
 
getNumColumns() - Method in class deepnetts.util.CsvFormat
 
getNumInputs() - Method in class deepnetts.data.TabularDataSet
 
getNumOutputs() - Method in class deepnetts.data.TabularDataSet
 
getOptimizer() - Method in class deepnetts.net.layers.AbstractLayer
 
getOptimizer() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getOptimizerType() - Method in class deepnetts.net.layers.AbstractLayer
 
getOutput() - Method in class deepnetts.net.NeuralNetwork
Returns network's output.
getOutput(float[]) - Method in class deepnetts.net.FeedForwardNetwork
Returns network output for the given input.
getOutputErrors() - Method in class deepnetts.net.layers.OutputLayer
 
getOutputLabel(int) - Method in class deepnetts.net.NeuralNetwork
 
getOutputLabels() - Method in class deepnetts.net.NeuralNetwork
 
getOutputLayer() - Method in class deepnetts.net.NeuralNetwork
 
getOutputs() - Method in class deepnetts.net.layers.AbstractLayer
 
getOutputs() - Method in interface deepnetts.net.layers.Layer
Returns layer outputs (as a tensor).
getPerformanceByClass() - Method in class deepnetts.eval.ClassifierEvaluator
 
getPrecision() - Method in class deepnetts.eval.ClassificationMetrics
What percent of those predicted as positive are really positive.
getPreprocessing() - Method in class deepnetts.net.NeuralNetwork
 
getPrevBiasSqrSum() - Method in class deepnetts.net.layers.AbstractLayer
 
getPrevDeltaBiases() - Method in class deepnetts.net.layers.AbstractLayer
 
getPrevDeltaWeights() - Method in class deepnetts.net.layers.AbstractLayer
 
getPrevGradSqrSum() - Method in class deepnetts.net.layers.AbstractLayer
 
getPrevlayer() - Method in class deepnetts.net.layers.AbstractLayer
 
getPrime(float) - Method in interface deepnetts.net.layers.activation.ActivationFunction
Returns the first derivative of activation function for specified output y
getPrime(float) - Method in class deepnetts.net.layers.activation.LeakyRelu
 
getPrime(float) - Method in class deepnetts.net.layers.activation.Linear
 
getPrime(float) - Method in class deepnetts.net.layers.activation.Relu
 
getPrime(float) - Method in class deepnetts.net.layers.activation.Sigmoid
 
getPrime(float) - Method in class deepnetts.net.layers.activation.Tanh
 
getProperties() - Method in class deepnetts.core.DeepNetts
 
getProperty(String) - Method in class deepnetts.core.DeepNetts
 
getRandom() - Method in class deepnetts.util.RandomGenerator
 
getRank() - Method in class deepnetts.util.Tensor
Rank corresponds to number of dimensions in tensor.
getRecall() - Method in class deepnetts.eval.ClassificationMetrics
Ratio between those classified as positive compared to those that are actually positive.
getRed(int) - Static method in class deepnetts.util.ColorUtils
 
getResizeStrategy() - Method in class deepnetts.data.ImageSet
 
getRgbVector() - Method in class deepnetts.data.ExampleImage
 
getRootMeanSquaredSum() - Method in class deepnetts.eval.MeanSquaredError
 
getRows() - Method in class deepnetts.util.Tensor
 
getScaleImages() - Method in class deepnetts.data.ImageSet
Returns flag that indicates wheather images should be scaled to specified dimensions while creating image set.
getScore() - Method in class deepnetts.util.BoundingBox
 
getShuffle() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getSnapshotEpochs() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getSnapshotPath() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getSource() - Method in class deepnetts.net.train.TrainingEvent
Gets the source of the event.
getSpecificity() - Method in class deepnetts.eval.ClassificationMetrics
Specificity or true negative rate.
getSquaredSum() - Method in class deepnetts.eval.MeanSquaredError
Returns squared error sum (RSS, or residual square sum)
getStride() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
getStride() - Method in class deepnetts.net.layers.Filter
 
getStride() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
getString(String) - Method in class deepnetts.util.Parameters
 
getString(String) - Method in class deepnetts.util.TypedProperties
 
getTargetNames() - Method in class deepnetts.data.ImageSet
Returns output/image labels.
getTargetNames() - Method in class deepnetts.data.TabularDataSet
 
getTargetOutput() - Method in class deepnetts.data.ExampleImage
 
getTargetOutput() - Method in interface deepnetts.data.MLDataItem
Returns target output for machine learning model of this item.
getTargetOutput() - Method in class deepnetts.data.TabularDataSet.Item
 
getTestSet() - Method in class deepnetts.data.TrainTestPair
 
getTestSet() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getThreadCount() - Method in class deepnetts.util.DeepNettsThreadPool
 
getThreshold() - Method in class deepnetts.eval.ClassifierEvaluator
 
getTotal() - Method in class deepnetts.eval.ClassificationMetrics
Returns total number of classifications.
getTotal() - Method in class deepnetts.eval.RootMeanSquaredError
 
getTotal() - Method in class deepnetts.net.loss.BinaryCrossEntropyLoss
 
getTotal() - Method in class deepnetts.net.loss.CrossEntropyLoss
 
getTotal() - Method in interface deepnetts.net.loss.LossFunction
Returns the total error calculated by this loss function.
getTotal() - Method in class deepnetts.net.loss.MeanSquaredErrorLoss
 
getTotalItems() - Method in class deepnetts.eval.ConfusionMatrix
 
getTrainer() - Method in class deepnetts.net.NeuralNetwork
 
getTrainer() - Method in interface deepnetts.net.train.TrainerProvider
 
getTrainingAccuracy() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getTrainingeSet() - Method in class deepnetts.data.TrainTestPair
 
getTrainingLoss() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getTrueNegative() - Method in class deepnetts.eval.ConfusionMatrix
 
getTrueNegative(int) - Method in class deepnetts.eval.ConfusionMatrix
 
getTruePositive() - Method in class deepnetts.eval.ConfusionMatrix
Return true positive for binary classification.
getTruePositive(int) - Method in class deepnetts.eval.ConfusionMatrix
Returns true positive for specified class idx for multiclass classification
getType() - Method in class deepnetts.net.train.TrainingEvent
Gets the type of the event.
getValidationAccuracy() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getValidationLoss() - Method in class deepnetts.net.train.BackpropagationTrainer
 
getValue() - Method in class deepnetts.util.Parameter
 
getValue(float) - Method in interface deepnetts.net.layers.activation.ActivationFunction
Returns the value of activation function for specified input x
getValue(float) - Method in class deepnetts.net.layers.activation.LeakyRelu
 
getValue(float) - Method in class deepnetts.net.layers.activation.Linear
 
getValue(float) - Method in class deepnetts.net.layers.activation.Relu
 
getValue(float) - Method in class deepnetts.net.layers.activation.Sigmoid
 
getValue(float) - Method in class deepnetts.net.layers.activation.Tanh
 
getValues() - Method in class deepnetts.util.Tensor
 
getWeights() - Method in class deepnetts.net.ConvolutionalNetwork
Returns all weights from this network as list of strings.
getWeights() - Method in class deepnetts.net.layers.AbstractLayer
 
getWidth() - Method in class deepnetts.data.ExampleImage
 
getWidth() - Method in class deepnetts.net.layers.AbstractLayer
 
getWidth() - Method in class deepnetts.net.layers.Filter
 
getWidth() - Method in class deepnetts.util.BoundingBox
 
getWithStride(int[]) - Method in class deepnetts.util.Tensor
 
getX() - Method in class deepnetts.util.BoundingBox
 
getY() - Method in class deepnetts.util.BoundingBox
 
getZeroMeanPixels() - Method in class deepnetts.data.ImageSet
 

H

handleEvent(TrainingEvent) - Method in class deepnetts.net.train.opt.AdaDeltaOptimizer
 
handleEvent(TrainingEvent) - Method in class deepnetts.net.train.opt.AdamOptimizer
 
handleEvent(TrainingEvent) - Method in class deepnetts.net.train.opt.LearningRateDecay
 
handleEvent(TrainingEvent) - Method in interface deepnetts.net.train.TrainingListener
Invoked when a training event occurs.
hashCode() - Method in class deepnetts.util.Tensor
 
he(float[], int) - Static method in class deepnetts.net.weights.RandomWeights
He initialization, used for relu activations.zero-mean.
HE - deepnetts.net.weights.RandomWeightsType
 
hiddenActivationFunction(ActivationType) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
hiddenActivationFunction(ActivationType) - Method in class deepnetts.net.FeedForwardNetwork.Builder
 

I

IMAGE_IDX_FILE - Static variable in class deepnetts.util.ImageSetUtils
 
ImagePreprocessing - Class in deepnetts.util
Used at inference time
ImagePreprocessing() - Constructor for class deepnetts.util.ImagePreprocessing
 
ImageResize - Enum in deepnetts.util
 
ImageSet - Class in deepnetts.data
Data set with images that will be used to train convolutional neural network.
ImageSet(int, int) - Constructor for class deepnetts.data.ImageSet
 
ImageSet(int, int, String) - Constructor for class deepnetts.data.ImageSet
 
ImageSetUtils - Class in deepnetts.util
 
ImageSetUtils() - Constructor for class deepnetts.util.ImageSetUtils
 
ImageUtils - Class in deepnetts.util
Utility methods to work with images.
inc(int, int) - Method in class deepnetts.eval.ConfusionMatrix
Increments matrix value at specified position.
init() - Method in class deepnetts.net.layers.AbstractLayer
This method should implement layer initialization when layer is added to network (create weights, outputs, deltas, randomization etc.)
init() - Method in class deepnetts.net.layers.ConvolutionalLayer
Init dimensions, create matrices, filters, weights, biases and all internal structures etc.
init() - Method in class deepnetts.net.layers.FlattenLayer
 
init() - Method in class deepnetts.net.layers.FullyConnectedLayer
Creates all internal data structures: inputs, weights, biases, outputs, deltas, deltaWeights, deltaBiases prevDeltaWeights, prevDeltaBiases.
init() - Method in class deepnetts.net.layers.FullyConnectedLayer1
Creates all internal data structures: inputs, weights, biases, outputs, deltas, deltaWeights, deltaBiases prevDeltaWeights, prevDeltaBiases.
init() - Method in class deepnetts.net.layers.InputLayer
Initialize this layer in network.
init() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
init() - Method in class deepnetts.net.layers.OutputLayer
 
init() - Method in class deepnetts.net.layers.SoftmaxOutputLayer
 
initSeed(long) - Static method in class deepnetts.net.weights.RandomWeights
Initializes random number generator with specified seed.
initSeed(long) - Method in class deepnetts.util.RandomGenerator
 
initTransientFields() - Method in class deepnetts.net.layers.AbstractLayer
 
initTransientFields() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
initTransientFields() - Method in class deepnetts.net.layers.FullyConnectedLayer
 
initTransientFields() - Method in class deepnetts.net.layers.FullyConnectedLayer1
 
initTransientFields() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
INPUT - deepnetts.net.layers.LayerType
 
InputLayer - Class in deepnetts.net.layers
Input layer in neural network, which accepts external input, and sends it to next layer in a network.
InputLayer(int) - Constructor for class deepnetts.net.layers.InputLayer
Creates input layer with specified width, and with height and depth equals to one.
InputLayer(int, int) - Constructor for class deepnetts.net.layers.InputLayer
Creates input layer with specified width and height, and depth=1 (single depth/channel).
InputLayer(int, int, int) - Constructor for class deepnetts.net.layers.InputLayer
Creates input layer with specified width, height, and depth (number of channels).
INTEGER - deepnetts.util.ColumnType
 
invert() - Method in class deepnetts.data.ExampleImage
 
isBatchMode() - Method in class deepnetts.net.layers.AbstractLayer
 
isBatchMode() - Method in class deepnetts.net.train.BackpropagationTrainer
 
isEnabled() - Method in class deepnetts.util.ImagePreprocessing
 
isHasHeader() - Method in class deepnetts.util.CsvFormat
 
isImageFile(File) - Method in class deepnetts.util.AugmentImagesTest
 
isImageFile(File) - Method in class deepnetts.util.DeleteAugmentImages
 
isImageFile(File) - Method in class deepnetts.util.RandomlyTranslateImages
 
isInvertPixels() - Method in class deepnetts.util.ImagePreprocessing
 
isSubMean() - Method in class deepnetts.util.ImagePreprocessing
 
ISSUED_DATE - Static variable in class deepnetts.util.LicenseChecker
 
isTrainable() - Method in class deepnetts.net.layers.AbstractLayer
 
Item(float[], float[]) - Constructor for class deepnetts.data.TabularDataSet.Item
 
Item(Tensor, Tensor) - Constructor for class deepnetts.data.TabularDataSet.Item
 
ITERATION_FINISHED - deepnetts.net.train.TrainingEvent.Type
Specifies a training iteration for (single data item) finished event
ITERATION_FINISHED - Static variable in class deepnetts.net.train.TrainingEvent
Specifies that training iteration has finished.

K

KFoldCrossValidation - Class in deepnetts.net.train
Split data set into k parts of equal sizes (folds), then train model with k-1 folds, and validate with remaining 1 fold.
KFoldCrossValidation.Builder - Class in deepnetts.net.train
 

L

LABELS_FILE - Static variable in class deepnetts.util.ImageSetUtils
 
labelsFromSubDirectories(String) - Static method in class deepnetts.util.ImageSetUtils
Returns a list of category/class labels from the names of subdirectories for the given path.
Layer - Interface in deepnetts.net.layers
Common base interface for all types of neural network layers.
LayerType - Enum in deepnetts.net.layers
Enum for supported types of layers.
LEAKY_RELU - deepnetts.net.layers.activation.ActivationType
 
LeakyRelu - Class in deepnetts.net.layers.activation
Leaky Rectified Linear Activation and its Derivative.
LeakyRelu() - Constructor for class deepnetts.net.layers.activation.LeakyRelu
 
LeakyRelu(float) - Constructor for class deepnetts.net.layers.activation.LeakyRelu
 
LearningRateDecay - Class in deepnetts.net.train.opt
https://www.coursera.org/learn/deep-neural-network/lecture/hjgIA/learning-rate-decay
LearningRateDecay(float, float) - Constructor for class deepnetts.net.train.opt.LearningRateDecay
 
LicenceException(String) - Constructor for exception deepnetts.util.LicenseChecker.LicenceException
 
LICENSE_NUMBER - Static variable in class deepnetts.util.LicenseChecker
 
LICENSE_TYPE - Static variable in class deepnetts.util.LicenseChecker
 
LicenseChecker - Class in deepnetts.util
https://github.com/verhas/License3j/wiki/sample Public key must be in jar file, in META-INF, as specified by PUB_KEY put license file in separate jar how to specify digest? - hardcode from private key
LicenseChecker() - Constructor for class deepnetts.util.LicenseChecker
 
LicenseChecker.LicenceException - Exception in deepnetts.util
 
Linear - Class in deepnetts.net.layers.activation
Linear activation function and its derivative y = x y' = 1
Linear() - Constructor for class deepnetts.net.layers.activation.Linear
 
LINEAR - deepnetts.net.layers.activation.ActivationType
 
listOf(Parameter...) - Static method in class deepnetts.util.Parameter
 
loadFileImageMapFromDirectory(File) - Static method in class deepnetts.util.ImageUtils
Loads JPG, JPEG or PNG images from specified directory and returns them as a map with File object as a key and BufferedImage object as a value.
loadImages(File) - Method in class deepnetts.data.ImageSet
Loads example images with corresponding labels from the specified file.
loadImages(File, int) - Method in class deepnetts.data.ImageSet
Loads specified number of example images with corresponding labels from the specified file.
loadImages(String) - Method in class deepnetts.data.ImageSet
 
loadImagesFromDirectory(File) - Static method in class deepnetts.util.ImageUtils
Loads all images from the specified directory, and returns them as a list.
loadLabels(File) - Method in class deepnetts.data.ImageSet
Loads and returns image labels to train neural network from the specified file.These labels will be used to label network's outputs.
loadLabels(String) - Method in class deepnetts.data.ImageSet
Loads and returns image labels to train neural network from the specified file.
lossFunction(LossType) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
lossFunction(LossType) - Method in class deepnetts.net.FeedForwardNetwork.Builder
Adds specified loss function to the network.
lossFunction(Class<? extends LossFunction>) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
LossFunction - Interface in deepnetts.net.loss
Base Interface for all loss functions.
LossType - Enum in deepnetts.net.loss
Supported types of Loss Functions in Deep Netts engine.

M

macroAverage(Collection<EvaluationMetrics>) - Static method in class deepnetts.eval.ClassifierEvaluator
Calculates macro average for the given list of perfromance measures.
macroAverage(Collection<EvaluationMetrics>) - Static method in class deepnetts.eval.RegresionEvaluator
 
main(String[]) - Static method in class deepnetts.util.AugmentImagesTest
 
main(String[]) - Static method in class deepnetts.util.CenterOnWhiteBackground
 
main(String[]) - Static method in class deepnetts.util.CreateImageIndex
 
main(String[]) - Static method in class deepnetts.util.CreateLabelsIndex
 
main(String[]) - Static method in class deepnetts.util.DeepNettsRunner
 
main(String[]) - Static method in class deepnetts.util.DeleteAugmentImages
 
main(String[]) - Static method in class deepnetts.util.GenerateRandomNegative
 
main(String[]) - Static method in class deepnetts.util.ObjectsOnBackgrounds
 
main(String[]) - Static method in class deepnetts.util.RandomlyTranslateImages
 
main(String[]) - Static method in class deepnetts.util.ScaleImages
 
MathFunctions - Class in deepnetts.net.layers.activation
Misc math utility functions.
max(float[]) - Static method in class deepnetts.util.StatUtils
 
MaxNormalizer - Class in deepnetts.data.norm
Performs max normalization, rescales data to corresponding max value in each column.
MaxNormalizer(DataSet<MLDataItem>) - Constructor for class deepnetts.data.norm.MaxNormalizer
Creates a new instance of max normalizer initialized to max values in given data set.
MAXPOOLING - deepnetts.net.layers.LayerType
 
MaxPoolingLayer - Class in deepnetts.net.layers
This layer performs max pooling operation in convolutional neural network, which scales down output from previous layer by taking max outputs from small predefined filter areas.
MaxPoolingLayer(int, int, int) - Constructor for class deepnetts.net.layers.MaxPoolingLayer
Creates a new max pooling layer with specified filter dimensions and stride.
mean() - Method in class deepnetts.util.Tensor
 
mean(float[]) - Static method in class deepnetts.util.StatUtils
 
MEAN_SQUARED_ERROR - deepnetts.net.loss.LossType
Mean Squared Error loss, used for regression tasks, implemented by MeanSquaredErrorLoss
MeanSquaredError - Class in deepnetts.eval
This class calculates values used for evaluation metrics for regression problems.
MeanSquaredError() - Constructor for class deepnetts.eval.MeanSquaredError
 
MeanSquaredErrorLoss - Class in deepnetts.net.loss
Mean Squared Error Loss function.
MeanSquaredErrorLoss(NeuralNetwork) - Constructor for class deepnetts.net.loss.MeanSquaredErrorLoss
Creates a new mean squared error loss for the given neural network.
min(float[]) - Static method in class deepnetts.util.StatUtils
 
MINI_BATCH - deepnetts.net.train.TrainingEvent.Type
Specifies a mini batch (batch of items) finished event
MINI_BATCH - Static variable in class deepnetts.net.train.TrainingEvent
Specifies mini batch event.
MinMaxNormalizer - Class in deepnetts.data.norm
Performs Min Max normalization on the given data set.
MinMaxNormalizer(DataSet<MLDataItem>) - Constructor for class deepnetts.data.norm.MinMaxNormalizer
Creates a new instance of max normalizer initialized to max values in given data set.
MLDataItem - Interface in deepnetts.data
Single data item that will be used to train machine learning model.
model(NeuralNetwork) - Method in class deepnetts.net.train.KFoldCrossValidation.Builder
 
MOMENTUM - deepnetts.net.train.opt.OptimizerType
 
MomentumOptimizer - Class in deepnetts.net.train.opt
Momentum optimization adds momentum parameter to basic Stochastic Gradient Descent, which can accelerate the process.
MomentumOptimizer(AbstractLayer) - Constructor for class deepnetts.net.train.opt.MomentumOptimizer
 
mserror - Variable in class deepnetts.eval.ClassificationMetrics.Stats
 
multiply(float) - Method in class deepnetts.util.Tensor
 
multiply(float[], float[]) - Static method in class deepnetts.util.Tensors
 
multiply(float, int) - Method in class deepnetts.util.Tensor
 
multiplyElementWise(Tensor) - Method in class deepnetts.util.Tensor
 

N

NAME - Static variable in class deepnetts.util.LicenseChecker
 
negativeFreqency() - Method in class deepnetts.eval.ClassificationMetrics
 
NETWORK_FILE_EXT - Static variable in class deepnetts.util.FileIO
 
NetworkType - Enum in deepnetts.net
Neural network architecture types
NeuralNetwork<T extends Trainer> - Class in deepnetts.net
Base class for all neural networks in Deep Netts.
nextFloat() - Method in class deepnetts.util.RandomGenerator
 
nextGaussian() - Method in class deepnetts.util.RandomGenerator
 
nextInt() - Method in class deepnetts.util.RandomGenerator
 
normal(float[]) - Static method in class deepnetts.net.weights.RandomWeights
 
normalize(DataSet<MLDataItem>) - Method in class deepnetts.data.norm.DecimalScaleNormalizer
Performs normalization on the given inputs.
normalize(DataSet<MLDataItem>) - Method in class deepnetts.data.norm.MaxNormalizer
Performs normalization on the given inputs.
normalize(DataSet<MLDataItem>) - Method in class deepnetts.data.norm.MinMaxNormalizer
Performs normalization on the given inputs.
normalize(DataSet<MLDataItem>) - Method in class deepnetts.data.norm.RangeNormalizer
Performs normalization on the given inputs.
normalize(DataSet<MLDataItem>) - Method in class deepnetts.data.norm.Standardizer
 
normalizeInput(Tensor) - Method in class deepnetts.data.norm.AbstractNormalizer
Normalize input of deployed model
normalizeInput(Tensor) - Method in class deepnetts.data.norm.DecimalScaleNormalizer
 
normalizeInput(Tensor) - Method in class deepnetts.data.norm.MaxNormalizer
 
normalizeInput(Tensor) - Method in class deepnetts.data.norm.MinMaxNormalizer
 
normalizeInput(Tensor) - Method in class deepnetts.data.norm.RangeNormalizer
 
normalizeInput(Tensor) - Method in class deepnetts.data.norm.Standardizer
 
normalizeMax(DataSet) - Static method in class deepnetts.data.DataSets
 
normalizeMinMax(DataSet) - Static method in class deepnetts.data.DataSets
 
numDimensions() - Method in class deepnetts.util.Shape
 
numSplits(int) - Method in class deepnetts.net.train.KFoldCrossValidation.Builder
 

O

ObjectsOnBackgrounds - Class in deepnetts.util
Center images on backgounds and save at target path.
ObjectsOnBackgrounds() - Constructor for class deepnetts.util.ObjectsOnBackgrounds
 
of(int...) - Static method in class deepnetts.util.Shape
 
of(Class) - Static method in enum deepnetts.net.loss.LossType
 
Of(Class) - Static method in enum deepnetts.net.NetworkType
 
oneHotEncode(String, String[]) - Static method in class deepnetts.data.DataSets
Returns one hot encoded vector for the given label(s).
ones(int) - Static method in class deepnetts.util.Tensors
 
optimize() - Method in class deepnetts.net.train.opt.AbstractOptimizer
 
Optimizer - Interface in deepnetts.net.train.opt
Optimization technique to tune network's weights parameters used by training algorithm.
OptimizerType - Enum in deepnetts.net.train.opt
Supported types of optimization methods used by back-propagation training algorithm.
OUTPUT - deepnetts.net.layers.LayerType
 
OutputLayer - Class in deepnetts.net.layers
Output layer of a neural network, which gives the final output of a network.
OutputLayer(int) - Constructor for class deepnetts.net.layers.OutputLayer
Creates an instance of output layer with specified width (number of outputs) and sigmoid activation function by default.
OutputLayer(int, ActivationType) - Constructor for class deepnetts.net.layers.OutputLayer
Creates an instance of output layer with specified width (number of outputs) and specified activation function.
OutputLayer(String[]) - Constructor for class deepnetts.net.layers.OutputLayer
Creates an instance of output layer with specified width (number of outputs) which corresponds to number of labels and sigmoid activation function by default.
OutputLayer(String[], ActivationType) - Constructor for class deepnetts.net.layers.OutputLayer
 

P

Parameter<T> - Class in deepnetts.util
 
Parameter(String, T) - Constructor for class deepnetts.util.Parameter
 
Parameters - Class in deepnetts.util
TODO: setMethod, throw meannigfull exceptions
Parameters() - Constructor for class deepnetts.util.Parameters
 
physicalCoreCount() - Static method in class deepnetts.util.PhysicalCores
Returns the number of "physical" hardware threads available.
PhysicalCores - Class in deepnetts.util
Static utility class for finding the number of physical CPU cores.
positiveFreqency() - Method in class deepnetts.eval.ClassificationMetrics
 
precision - Variable in class deepnetts.eval.ClassificationMetrics.Stats
 
Preprocessing<T> - Interface in deepnetts.data
Data pre-processing abstraction.
printLicense() - Method in class deepnetts.util.LicenseChecker
 
PROP_BATCH_MODE - Static variable in class deepnetts.net.train.BackpropagationTrainer
 
PROP_BATCH_SIZE - Static variable in class deepnetts.net.train.BackpropagationTrainer
 
PROP_IMAGE_HEIGHT - Static variable in class deepnetts.util.DeepNettsRunner
 
PROP_IMAGE_WIDTH - Static variable in class deepnetts.util.DeepNettsRunner
 
PROP_LABELS_FILE - Static variable in class deepnetts.util.DeepNettsRunner
 
PROP_LEARNING_RATE - Static variable in class deepnetts.net.train.BackpropagationTrainer
 
PROP_LEARNING_RATE - Static variable in class deepnetts.util.DeepNettsRunner
 
PROP_MAX_EPOCHS - Static variable in class deepnetts.net.train.BackpropagationTrainer
 
PROP_MAX_ERROR - Static variable in class deepnetts.net.train.BackpropagationTrainer
 
PROP_MAX_ERROR - Static variable in class deepnetts.util.DeepNettsRunner
 
PROP_MOMENTUM - Static variable in class deepnetts.net.train.BackpropagationTrainer
 
PROP_OPTIMIZER_TYPE - Static variable in class deepnetts.net.train.BackpropagationTrainer
 
PROP_TEST_FILE - Static variable in class deepnetts.util.DeepNettsRunner
 
PROP_TRAINING_FILE - Static variable in class deepnetts.util.DeepNettsRunner
 
put(Parameter<?>) - Method in class deepnetts.util.Parameters
 

R

random(int, int) - Static method in class deepnetts.util.Tensors
Generate and return random tensor with specified number of rows and cols.
random(int, int, int) - Static method in class deepnetts.util.Tensors
 
random(int, int, int, int) - Static method in class deepnetts.util.Tensors
 
randomCrop(BufferedImage, int, int) - Static method in class deepnetts.util.ImageUtils
 
randomCrop(BufferedImage, int, int, int, Random) - Static method in class deepnetts.util.ImageUtils
Crops specified number of random subimages of specified dimensions.
RandomGenerator - Class in deepnetts.util
Random number generator singleton.
randomize() - Method in class deepnetts.util.Tensor
Randomize all values in tensor
randomize(float[]) - Static method in class deepnetts.net.weights.RandomWeights
Initialize the elements of specified array with random numbers with uniform distribution in range [-0.5, 0.5].
RandomlyTranslateImages - Class in deepnetts.util
just move 2(x) pix to left right up down
RandomlyTranslateImages() - Constructor for class deepnetts.util.RandomlyTranslateImages
 
randomSeed(long) - Method in class deepnetts.net.ConvolutionalNetwork.Builder
 
randomSeed(long) - Method in class deepnetts.net.FeedForwardNetwork.Builder
Initializes random number generator with specified seed in order to get same random number sequences (used for weights initialization).
randomTintAndBrightness(BufferedImage, float, int, int, Random) - Static method in class deepnetts.util.ImageUtils
Still not working as it should
randomTranslateImage(BufferedImage, int, int) - Static method in class deepnetts.util.ImageUtils
Returns an array of images created by translating specified input image by specified number of count with specified step size.
RandomWeights - Class in deepnetts.net.weights
Weights randomization utility methods.
RandomWeights() - Constructor for class deepnetts.net.weights.RandomWeights
 
RandomWeightsType - Enum in deepnetts.net.weights
Types of supported weights randomization techniques.
RangeNormalizer - Class in deepnetts.data.norm
Normalize data set to specified range.
RangeNormalizer(float, float) - Constructor for class deepnetts.data.norm.RangeNormalizer
Creates a new instance of range normalizer initialized to given min and max values.
readCsv(File, int, int, boolean, String) - Static method in class deepnetts.data.DataSets
Creates and returns data set from specified CSV file.
readCsv(String, int, int) - Static method in class deepnetts.data.DataSets
Create data set from CSV file, using coma (,) as default delimiter and no header (column names) in first row.
readCsv(String, int, int, boolean) - Static method in class deepnetts.data.DataSets
 
readCsv(String, int, int, boolean, String) - Static method in class deepnetts.data.DataSets
 
readCsv(String, int, int, String) - Static method in class deepnetts.data.DataSets
 
recall - Variable in class deepnetts.eval.ClassificationMetrics.Stats
 
RegresionEvaluator - Class in deepnetts.eval
Evaluates regressor neural network for specified data set.
RegresionEvaluator() - Constructor for class deepnetts.eval.RegresionEvaluator
 
Relu - Class in deepnetts.net.layers.activation
Rectified Linear Activation and its Derivative.
Relu() - Constructor for class deepnetts.net.layers.activation.Relu
 
RELU - deepnetts.net.layers.activation.ActivationType
 
removeListener(TrainingListener) - Method in class deepnetts.net.train.BackpropagationTrainer
 
renameFilesAsClasses(String, String) - Static method in class deepnetts.util.ImageSetUtils
Renames files in specified directory.
replace(float, float) - Method in class deepnetts.util.Tensor
 
reset() - Method in class deepnetts.net.loss.BinaryCrossEntropyLoss
 
reset() - Method in class deepnetts.net.loss.CrossEntropyLoss
 
reset() - Method in interface deepnetts.net.loss.LossFunction
Resets the total error and pattern counter.
reset() - Method in class deepnetts.net.loss.MeanSquaredErrorLoss
 
RMSPROP - deepnetts.net.train.opt.OptimizerType
 
RmsPropOptimizer - Class in deepnetts.net.train.opt
A variation of AdaDelta optimizer.
RmsPropOptimizer(AbstractLayer) - Constructor for class deepnetts.net.train.opt.RmsPropOptimizer
 
RootMeanSquaredError - Class in deepnetts.eval
A measure of error for regression tasks.
RootMeanSquaredError() - Constructor for class deepnetts.eval.RootMeanSquaredError
 
ROW_IDX - Static variable in interface deepnetts.net.train.opt.Optimizer
 
ROW_IDX - Static variable in class deepnetts.util.Shape
 
run() - Method in class deepnetts.net.train.KFoldCrossValidation
 
run() - Method in class deepnetts.util.AugmentImagesTest
 
run() - Method in class deepnetts.util.DeleteAugmentImages
 
run() - Method in class deepnetts.util.RandomlyTranslateImages
 
run() - Method in class deepnetts.util.ScaleImages
 
run(Runnable) - Method in class deepnetts.util.DeepNettsThreadPool
 
run(String) - Method in class deepnetts.util.DeepNettsRunner
 
run(Collection<Callable<Void>>) - Method in class deepnetts.util.DeepNettsThreadPool
 

S

scaleAndCenter(BufferedImage, int, int, int, Color) - Static method in class deepnetts.util.ImageUtils
Scales input image to specified target width or height, centers and returns resulting image.Scaling factor is calculated using larger dimension (width or height).
scaleBySmallerAndCrop(BufferedImage, int, int) - Static method in class deepnetts.util.ImageUtils
Scales input image to specified target width or height, crops and returns resulting image.
scaleImage(BufferedImage, int, int) - Static method in class deepnetts.util.ImageUtils
Scales specified image and returns new image with specified dimensions.
ScaleImages - Class in deepnetts.util
 
ScaleImages() - Constructor for class deepnetts.util.ScaleImages
 
set(float, int) - Method in class deepnetts.util.Tensor
Sets value at specified index position.
set(float, int, int) - Method in class deepnetts.util.Tensor
Set value at specified tensor's [row, col] position.
set(float, int, int, int) - Method in class deepnetts.util.Tensor
 
set(float, int, int, int, int) - Method in class deepnetts.util.Tensor
 
setActivation(ActivationFunction) - Method in class deepnetts.net.layers.AbstractLayer
 
setActivationType(ActivationType) - Method in class deepnetts.net.layers.AbstractLayer
 
setBatchMode(boolean) - Method in class deepnetts.net.layers.AbstractLayer
 
setBatchMode(boolean) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setBatchSize(int) - Method in class deepnetts.net.layers.AbstractLayer
 
setBatchSize(int) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setBiases(float[]) - Method in class deepnetts.net.layers.AbstractLayer
 
setCheckpointEpochs(int) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setClassLabel(String) - Method in class deepnetts.eval.ClassificationMetrics
 
setColumnNames(String[]) - Method in class deepnetts.data.TabularDataSet
 
setColumnNames(String[]) - Method in class deepnetts.util.CsvFormat
 
setColumnTypes(ColumnType[]) - Method in class deepnetts.util.CsvFormat
 
setConfusionMatrix(ConfusionMatrix) - Method in class deepnetts.eval.ClassifierEvaluationResult
 
setDelimiter(String) - Method in class deepnetts.data.ImageSet
 
setDelimiter(String) - Method in class deepnetts.util.CsvFormat
 
setDeltas(Tensor) - Method in class deepnetts.net.layers.AbstractLayer
 
setDropout(float) - Method in class deepnetts.net.layers.FullyConnectedLayer
 
setDropout(float) - Method in class deepnetts.net.layers.FullyConnectedLayer1
 
setDropout(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setEarlyStopping(boolean) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setEarlyStoppingMinDelta(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setEarlyStoppingPatience(int) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setEnabled(boolean) - Method in class deepnetts.util.ImagePreprocessing
 
setFilters(Tensor) - Method in class deepnetts.net.layers.ConvolutionalLayer
 
setFilters(String) - Method in class deepnetts.net.layers.ConvolutionalLayer
 
setHasHeader(boolean) - Method in class deepnetts.util.CsvFormat
 
setId(int) - Method in class deepnetts.util.BoundingBox
 
setInput(float[]) - Method in class deepnetts.net.FeedForwardNetwork
 
setInput(Tensor) - Method in class deepnetts.net.ConvolutionalNetwork
 
setInput(Tensor) - Method in class deepnetts.net.layers.InputLayer
Sets network input
setInput(Tensor) - Method in class deepnetts.net.NeuralNetwork
Sets network input vector and triggers forward pass.
setInvertImages(boolean) - Method in class deepnetts.data.ImageSet
 
setInvertPixels(boolean) - Method in class deepnetts.util.ImagePreprocessing
 
setL1Regularization(float) - Method in class deepnetts.net.layers.AbstractLayer
 
setL1Regularization(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setL2Regularization(float) - Method in class deepnetts.net.layers.AbstractLayer
 
setL2Regularization(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setLabel(String) - Method in class deepnetts.net.NeuralNetwork
 
setLabel(String) - Method in class deepnetts.util.BoundingBox
 
setLearningRate(float) - Method in class deepnetts.net.layers.AbstractLayer
 
setLearningRate(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setLearningRate(float) - Method in class deepnetts.net.train.opt.AdaDeltaOptimizer
 
setLearningRate(float) - Method in class deepnetts.net.train.opt.AdaGradOptimizer
 
setLearningRate(float) - Method in class deepnetts.net.train.opt.AdamOptimizer
 
setLearningRate(float) - Method in class deepnetts.net.train.opt.MomentumOptimizer
 
setLearningRate(float) - Method in interface deepnetts.net.train.opt.Optimizer
 
setLearningRate(float) - Method in class deepnetts.net.train.opt.RmsPropOptimizer
 
setLearningRate(float) - Method in class deepnetts.net.train.opt.SgdOptimizer
 
setLearningRateDecay(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setLossFunction(LossFunction) - Method in class deepnetts.net.NeuralNetwork
 
setLossType(LossType) - Method in class deepnetts.net.layers.OutputLayer
 
setMaxEpochs(long) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setMaxError(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setMaxInputs(Tensor) - Method in class deepnetts.data.norm.MaxNormalizer
 
setMaxOutputs(Tensor) - Method in class deepnetts.data.norm.MaxNormalizer
 
setMean(Tensor) - Method in class deepnetts.util.ImagePreprocessing
 
setMomentum(float) - Method in class deepnetts.net.layers.AbstractLayer
 
setMomentum(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setNextlayer(AbstractLayer) - Method in class deepnetts.net.layers.AbstractLayer
 
setNormalizer(AbstractNormalizer) - Method in class deepnetts.net.NeuralNetwork
 
setOptimizer(OptimizerType) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setOptimizerType(OptimizerType) - Method in class deepnetts.net.layers.AbstractLayer
 
setOutputError(float[]) - Method in class deepnetts.net.NeuralNetwork
 
setOutputErrors(float[]) - Method in class deepnetts.net.layers.OutputLayer
 
setOutputLabels(String...) - Method in class deepnetts.net.NeuralNetwork
 
setOutputs(Tensor) - Method in class deepnetts.net.layers.AbstractLayer
 
setPreprocessing(Preprocessing<Tensor>) - Method in class deepnetts.net.NeuralNetwork
 
setPrevDeltaWeights(Tensor) - Method in class deepnetts.net.layers.AbstractLayer
 
setPrevLayer(AbstractLayer) - Method in class deepnetts.net.layers.AbstractLayer
 
setProperties(Properties) - Method in class deepnetts.net.train.BackpropagationTrainer
Sets properties from available keys in specified prop object.
setResizeStrategy(ImageResize) - Method in class deepnetts.data.ImageSet
 
setScaleImages(boolean) - Method in class deepnetts.data.ImageSet
 
setScore(float) - Method in class deepnetts.util.BoundingBox
 
setShuffle(boolean) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setSnapshotEpochs(int) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setSnapshotPath(String) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setSubMean(boolean) - Method in class deepnetts.util.ImagePreprocessing
 
setTargetOutput(Tensor) - Method in class deepnetts.data.ExampleImage
 
setTestSet(DataSet<MLDataItem>) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setThreshold(float) - Method in class deepnetts.eval.ClassifierEvaluator
 
setTrainable(boolean) - Method in class deepnetts.net.layers.AbstractLayer
Set trainable to false to freeze learned weights.
setTrainer(T) - Method in class deepnetts.net.NeuralNetwork
 
setTrainer(T) - Method in interface deepnetts.net.train.TrainerProvider
 
setTrainingSnapshots(boolean) - Method in class deepnetts.net.train.BackpropagationTrainer
 
setValues(float...) - Method in class deepnetts.util.Tensor
 
setValuesFromString(String) - Method in class deepnetts.util.Tensor
Sets tensor values from csv string.
setWeights(Tensor) - Method in class deepnetts.net.layers.AbstractLayer
 
setWeights(String) - Method in class deepnetts.net.layers.AbstractLayer
 
setWeights(List<String>) - Method in class deepnetts.net.ConvolutionalNetwork
 
SGD - deepnetts.net.train.opt.OptimizerType
Stochastic Gradient Descent, a basic type of neural network optimization algorithm.
SgdOptimizer - Class in deepnetts.net.train.opt
Basic Stochastic Gradient Descent optimization algorithm, which iteratively change weights towards value which gives minimum error.
SgdOptimizer(AbstractLayer) - Constructor for class deepnetts.net.train.opt.SgdOptimizer
 
Shape - Class in deepnetts.util
Immutable class that represents Tensor shape.
Shape(int[]) - Constructor for class deepnetts.util.Shape
 
shuffle() - Method in class deepnetts.data.TabularDataSet
Shuffles the data set items using the default random generator.
shuffle(int) - Method in class deepnetts.data.TabularDataSet
Shuffles data set items using java random generator initializes with specified seed
shutdown() - Static method in class deepnetts.core.DeepNetts
 
shutdown() - Method in class deepnetts.util.DeepNettsThreadPool
 
shutdownNow() - Method in class deepnetts.util.DeepNettsThreadPool
 
Sigmoid - Class in deepnetts.net.layers.activation
Sigmoid activation function
Sigmoid() - Constructor for class deepnetts.net.layers.activation.Sigmoid
 
SIGMOID - deepnetts.net.layers.activation.ActivationType
 
size() - Method in class deepnetts.util.Tensor
Total number of values in tensor.
size(int) - Static method in class deepnetts.net.layers.Filter
 
SOFTMAX - deepnetts.net.layers.activation.ActivationType
 
SoftmaxOutputLayer - Class in deepnetts.net.layers
Output layer with softmax activation function.
SoftmaxOutputLayer(int) - Constructor for class deepnetts.net.layers.SoftmaxOutputLayer
 
SoftmaxOutputLayer(String[]) - Constructor for class deepnetts.net.layers.SoftmaxOutputLayer
 
split(double...) - Method in class deepnetts.data.ImageSet
Splits data set into several parts specified by the input parameter partSizes.
split(double...) - Method in class deepnetts.data.TabularDataSet
Splits data set into several parts specified by the input parameter partSizes.
split(int) - Method in class deepnetts.data.TabularDataSet
Split data set into specified number of part of equal sizes.
sqrt() - Method in class deepnetts.util.Tensor
 
standardDeviation(float[], float) - Static method in class deepnetts.util.StatUtils
 
Standardizer - Class in deepnetts.data.norm
Performs standardization on inputs in order to get desired statistical properties of the data set (zero mean and one standard deviation).
Standardizer(DataSet<MLDataItem>) - Constructor for class deepnetts.data.norm.Standardizer
 
STARTED - deepnetts.net.train.TrainingEvent.Type
Specifies a training started event
STARTED - Static variable in class deepnetts.net.train.TrainingEvent
Specifies that training has started.
Stats() - Constructor for class deepnetts.eval.ClassificationMetrics.Stats
 
StatUtils - Class in deepnetts.util
 
StatUtils() - Constructor for class deepnetts.util.StatUtils
 
std(float) - Method in class deepnetts.util.Tensor
 
stop() - Method in class deepnetts.net.train.BackpropagationTrainer
 
STOPPED - deepnetts.net.train.TrainingEvent.Type
Specifies a training stopped event
STOPPED - Static variable in class deepnetts.net.train.TrainingEvent
Specifies that training has stopped.
STRATCH - deepnetts.util.ImageResize
 
stride(int) - Method in class deepnetts.net.layers.Filter
 
STRING - deepnetts.util.ColumnType
 
sub(float) - Method in class deepnetts.util.Tensor
 
sub(float[], float) - Static method in class deepnetts.util.Tensors
 
sub(float[], float[]) - Static method in class deepnetts.util.Tensors
 
sub(float, int, int) - Method in class deepnetts.util.Tensor
 
sub(float, int, int, int) - Method in class deepnetts.util.Tensor
 
sub(float, int, int, int, int) - Method in class deepnetts.util.Tensor
 
sub(Tensor) - Method in class deepnetts.util.Tensor
Subtracts specified tensor t from this tensor.
sub(Tensor, Tensor) - Static method in class deepnetts.util.Tensor
Subtracts tensor t2 from t1.
submit(Callable<?>) - Method in class deepnetts.util.DeepNettsThreadPool
Submit a single task to thread pool.
sumAbs() - Method in class deepnetts.util.Tensor
Returns sum of abs values of this tensor - L1 norm
sumSqr() - Method in class deepnetts.util.Tensor
Returns sum of squared values of this tensor - L2 norm

T

TabularDataSet<T extends MLDataItem> - Class in deepnetts.data
Basic data set with tabular data.
TabularDataSet(int, int) - Constructor for class deepnetts.data.TabularDataSet
Create a new instance of BasicDataSet with specified size of input and output.
TabularDataSet.Item - Class in deepnetts.data
Represents a basic data set item (single row) with input tensor and target vector in a data set.
TabularDataSetStats - Class in deepnetts.util
 
TabularDataSetStats(TabularDataSet) - Constructor for class deepnetts.util.TabularDataSetStats
 
Tanh - Class in deepnetts.net.layers.activation
Hyperbolic tangens activation function
Tanh() - Constructor for class deepnetts.net.layers.activation.Tanh
 
TANH - deepnetts.net.layers.activation.ActivationType
 
Tensor - Class in deepnetts.util
This class represents multidimensional array/matrix (can be 1D, 2D, 3D or 4D).
Tensor(float...) - Constructor for class deepnetts.util.Tensor
Creates a single row tensor with specified values.
Tensor(float[][]) - Constructor for class deepnetts.util.Tensor
Creates a 2D tensor / matrix with specified values.
Tensor(float[][][]) - Constructor for class deepnetts.util.Tensor
Creates a 3D tensor from specified 3D array
Tensor(float[][][][]) - Constructor for class deepnetts.util.Tensor
 
Tensor(int) - Constructor for class deepnetts.util.Tensor
Creates an empty single row tensor with specified number of columns.
Tensor(int, float) - Constructor for class deepnetts.util.Tensor
 
Tensor(int, int) - Constructor for class deepnetts.util.Tensor
Creates a tensor with specified number of rows and columns.
Tensor(int, int, float[]) - Constructor for class deepnetts.util.Tensor
 
Tensor(int, int, int) - Constructor for class deepnetts.util.Tensor
Creates a 3D tensor with specified number of rows, cols and depth.
Tensor(int, int, int, float[]) - Constructor for class deepnetts.util.Tensor
 
Tensor(int, int, int, int) - Constructor for class deepnetts.util.Tensor
 
Tensor(int, int, int, int, float[]) - Constructor for class deepnetts.util.Tensor
 
Tensor(Shape, float...) - Constructor for class deepnetts.util.Tensor
 
Tensor(Tensor) - Constructor for class deepnetts.util.Tensor
Public deep copy / clone constructor.
Tensors - Class in deepnetts.util
Static utility methods for tensors.
test(DataSet<? extends MLDataItem>) - Method in class deepnetts.net.NeuralNetwork
 
TEST_FILE - Static variable in class deepnetts.util.ImageSetUtils
 
toJson(NeuralNetwork<?>) - Static method in class deepnetts.util.FileIO
Returns JSON representation of specified neural network object.
toString() - Method in class deepnetts.data.TabularDataSet.Item
 
toString() - Method in class deepnetts.eval.ClassificationMetrics.Stats
 
toString() - Method in class deepnetts.eval.ClassificationMetrics
 
toString() - Method in class deepnetts.eval.ClassifierEvaluator
 
toString() - Method in class deepnetts.eval.ConfusionMatrix
 
toString() - Method in class deepnetts.net.layers.ConvolutionalLayer
 
toString() - Method in class deepnetts.net.layers.FullyConnectedLayer
 
toString() - Method in class deepnetts.net.layers.FullyConnectedLayer1
 
toString() - Method in class deepnetts.net.layers.InputLayer
 
toString() - Method in enum deepnetts.net.layers.LayerType
 
toString() - Method in class deepnetts.net.layers.MaxPoolingLayer
 
toString() - Method in class deepnetts.net.layers.OutputLayer
 
toString() - Method in enum deepnetts.net.loss.LossType
 
toString() - Method in enum deepnetts.net.NetworkType
 
toString() - Method in class deepnetts.net.NeuralNetwork
 
toString() - Method in class deepnetts.util.BoundingBox
 
toString() - Method in class deepnetts.util.CsvFormat
 
toString() - Method in class deepnetts.util.Parameter
 
toString() - Method in class deepnetts.util.Tensor
 
train(DataSet<?>, double) - Method in class deepnetts.net.train.BackpropagationTrainer
 
train(DataSet<? extends MLDataItem>) - Method in class deepnetts.net.NeuralNetwork
 
train(DataSet<? extends MLDataItem>) - Method in class deepnetts.net.train.BackpropagationTrainer
Run training using specified training set.
train(DataSet<? extends MLDataItem>) - Method in interface deepnetts.net.train.Trainer
Trains this model using specified training set.
train(DataSet<MLDataItem>, DataSet<MLDataItem>) - Method in class deepnetts.net.train.BackpropagationTrainer
Run training using specified training and validation sets.
TRAIN_FILE - Static variable in class deepnetts.util.ImageSetUtils
 
Trainer - Interface in deepnetts.net.train
Generic interface for deep learning training algorithm.
TrainerProvider<T extends Trainer> - Interface in deepnetts.net.train
This interface is implemented by trainable deep learning models, in order to provide access to training algorithm.
TrainingEvent - Class in deepnetts.net.train
TrainingEvent is used to notify interested parties that training event has happened.
TrainingEvent(BackpropagationTrainer, TrainingEvent.Type) - Constructor for class deepnetts.net.train.TrainingEvent
Constructs a new TrainingEvent with specified source and type.
TrainingEvent.Type - Enum in deepnetts.net.train
Type of the training event.
TrainingListener - Interface in deepnetts.net.train
The listener interface for receiving notifications of training events.
trainingSet(DataSet) - Method in class deepnetts.net.train.KFoldCrossValidation.Builder
 
TrainTestPair - Class in deepnetts.data
Training and test data set pair.
TrainTestPair(DataSet, DataSet) - Constructor for class deepnetts.data.TrainTestPair
 
trainTestSplit(DataSet<?>, double) - Static method in class deepnetts.data.DataSets
 
TRUE_NEGATIVE - Static variable in class deepnetts.eval.ConfusionMatrix
A label for items classified as negative which are really negative.
TRUE_POSITIVE - Static variable in class deepnetts.eval.ConfusionMatrix
A label for items classified as positive which are really positive.
TypedProperties - Class in deepnetts.util
 
TypedProperties() - Constructor for class deepnetts.util.TypedProperties
 

U

uniform(float[], float, float) - Static method in class deepnetts.net.weights.RandomWeights
 
uniform(float[], int) - Static method in class deepnetts.net.weights.RandomWeights
Uniform U[-a,a] where a=1/sqrt(in).
UNIFORM - deepnetts.net.weights.RandomWeightsType
 
updateLearningRate(float) - Method in class deepnetts.net.train.BackpropagationTrainer
 

V

VALID_UNTIL_DATE - Static variable in class deepnetts.util.LicenseChecker
 
valueFor(NeuralNetwork, DataSet<? extends MLDataItem>) - Method in interface deepnetts.net.loss.LossFunction
Calculates and returns loss function value for the given neural network and data set.
valueOf(String) - Static method in enum deepnetts.net.layers.activation.ActivationType
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.net.layers.LayerType
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.net.loss.LossType
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.net.NetworkType
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.net.train.opt.OptimizerType
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.net.train.TrainingEvent.Type
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.net.weights.RandomWeightsType
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.util.ColumnType
Returns the enum constant of this type with the specified name.
valueOf(String) - Static method in enum deepnetts.util.ImageResize
Returns the enum constant of this type with the specified name.
values() - Static method in enum deepnetts.net.layers.activation.ActivationType
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.net.layers.LayerType
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.net.loss.LossType
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.net.NetworkType
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.net.train.opt.OptimizerType
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.net.train.TrainingEvent.Type
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.net.weights.RandomWeightsType
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.util.ColumnType
Returns an array containing the constants of this enum type, in the order they are declared.
values() - Static method in enum deepnetts.util.ImageResize
Returns an array containing the constants of this enum type, in the order they are declared.
valuesAsString(Tensor[]) - Static method in class deepnetts.util.Tensor
 
variance(float[], float) - Static method in class deepnetts.util.StatUtils
 
version() - Method in class deepnetts.core.DeepNetts
 

W

WIDDROW_HOFF - deepnetts.net.weights.RandomWeightsType
 
widrowHoff(float[], float, float) - Static method in class deepnetts.net.weights.RandomWeights
 
writeImages(List<BufferedImage>, String, String, String) - Static method in class deepnetts.util.ImageUtils
Writes list of images to specified file path.
writeToFile(NeuralNetwork, String) - Static method in class deepnetts.util.FileIO
Serializes specified neural network to file with specified file.
writeToFile(List<String>, String) - Static method in class deepnetts.util.ImageSetUtils
Writes a specified list of strings to file.
writeToFileAsJson(NeuralNetwork, String) - Static method in class deepnetts.util.FileIO
 

X

xavier(float[], int, int) - Static method in class deepnetts.net.weights.RandomWeights
Normalized uniform initialization U[-a,a] with a = sqrt(6/(in + out)).
XAVIER - deepnetts.net.weights.RandomWeightsType
 

Z

zeroMean() - Method in class deepnetts.data.ImageSet
Applies zero mean normalization to entire dataset, and returns mean tensor.
zeros(int) - Static method in class deepnetts.util.Tensors
 
A B C D E F G H I K L M N O P R S T U V W X Z 
All Classes All Packages